feat(ASI): add behavioral trust evidence type specification#819
Open
0xbrainkid wants to merge 3 commits intoOWASP:mainfrom
Open
feat(ASI): add behavioral trust evidence type specification#8190xbrainkid wants to merge 3 commits intoOWASP:mainfrom
0xbrainkid wants to merge 3 commits intoOWASP:mainfrom
Conversation
Adds a formal evidence type definition for behavioral trust scoring as a control class input to ASI01-ASI03 runtime enforcement. Includes: - Evidence structure (trust_score, drift_status, verification) - Trust scoring formula: success_rate × confidence(volume), per-task-class - Enforceability classification: strong / bounded / detectable-only - Integration points: OWASP admissibility predicates, mutation boundary (MITRE), TrustProvider interface (W3C/LangGraph) - Security considerations: Sybil resistance, temporal decay, cold-start Referenced from discussion OWASP#802 (Runtime Enforcement Mapping).
0xbrainkid
requested review from
guerilla7,
hoeg and
itskerenkatz
as code owners
added 2 commits
April 7, 2026 18:54
…table fingerprint Per @desiorac's review in issue OWASP#802: baseline_version (opaque string) was insufficient because it doesn't provide the monotonic reference property needed for replay-verifiable proofs. Replaced with: - baseline_snapshot_hash: SHA-256 of canonicalized baseline (JCS) - baseline_snapshot_ts: when baseline was computed - Added MUST requirement: verifiers reject enforcement-mode evidence without this field
Per @desiorac review: high-volume read-only calls inflate confidence for the whole agent, allowing write/payment operations to reach 'strong' enforceability on borrowed trust. Fix: gates MUST evaluate task_class-scoped evidence. cross_class_score is optional for display but MUST NOT be used for enforcement decisions. Enforceability tier is now task-class-specific.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a formal behavioral trust evidence type specification to the ASI agentic top 10 documentation. This addresses the gap identified in issue #802 around formalizing behavioral trust as a control class for runtime enforcement.
Per @desiorac's invitation in issue #802.
What it adds
A standardized evidence type for expressing agent behavioral trustworthiness as an input to admissibility predicates at mutation boundaries.
success_rate × confidence(volume), scoped per task class — deterministic, auditable, no ML requiredConnections to existing work